Step... (31000/50000 | Loss: 1.604581594467163, Acc: 0.6744211912155151): 62%|█████████████████▍ | 31239/50000 [12:32:24<7:08:13, 1.37s/it]

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab9e1ec9fe5381c6cd01fb75c25867879a3e432dfaf4960054ef157b5e52d406
+oid sha256:0f9fa29e534a0b52f07cbcbf30350fd1deb85efed567bf2b958e563dee74a936
 size 249750019

outputs/checkpoints/checkpoint-25000/training_state.json

@@ -1 +0,0 @@
-{"step": 25001}

outputs/checkpoints/checkpoint-26000/training_state.json

@@ -1 +0,0 @@
-{"step": 26001}

outputs/checkpoints/{checkpoint-25000 → checkpoint-30000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f01f7bd9dc37008fe586042d0858630facb5e28a5aabe227d941a460b9dac62
+oid sha256:4f490e826683c621d4235a0f6be4d6447e58fec7dcaedf37c9c6b23ac1179860
 size 249750019

outputs/checkpoints/{checkpoint-25000 → checkpoint-30000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4e308d24cbf75134aac7314daf08bd6739fe89d8e0c1dc9de2428e0a4a588a
+oid sha256:9cb63864317874863355bb060661587e535ec09909bdec8699a4445bd3e1d2bd
 size 499500278

outputs/checkpoints/checkpoint-30000/training_state.json

@@ -0,0 +1 @@
+{"step": 30001}

outputs/checkpoints/{checkpoint-26000 → checkpoint-31000}/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ceb7903825a5802361e2abfa48cc22549619333ade477fa0502eca94fff7518
+oid sha256:0f9fa29e534a0b52f07cbcbf30350fd1deb85efed567bf2b958e563dee74a936
 size 249750019

outputs/checkpoints/{checkpoint-26000 → checkpoint-31000}/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22861588524628232613a207d4ef751ae2280267840c912f9817827bd0747a14
+oid sha256:74879c5519aa133f282d7c3b040183a11d8d6c38f0a04dde3bbcdb2f11f62b4e
 size 499500278

outputs/checkpoints/checkpoint-31000/training_state.json

@@ -0,0 +1 @@
+{"step": 31001}

outputs/events.out.tfevents.1627258355.tablespoon.3000110.3.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4371c0c54c365271287a80d90ab3836df6db4026abad278a225bc389a870e17
-size 4296275
+oid sha256:c50283b6813a75c683baf41ae4dc9ce87bc1ee96ad10f1cb1b2d5dd2d946fc32
+size 4594839

outputs/flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab9e1ec9fe5381c6cd01fb75c25867879a3e432dfaf4960054ef157b5e52d406
+oid sha256:0f9fa29e534a0b52f07cbcbf30350fd1deb85efed567bf2b958e563dee74a936
 size 249750019

outputs/optimizer_state.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54e623bbd0f1873163b786ac2b8889bdc078c9a03f02878216a3a20fb1d27569
+oid sha256:74879c5519aa133f282d7c3b040183a11d8d6c38f0a04dde3bbcdb2f11f62b4e
 size 499500278

outputs/training_state.json

@@ -1 +1 @@
-{"step": 29001}
+{"step": 31001}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d7187b7156584b95e4c067f8b7d04c6f66b165d9d934533bd83dc404dc48c81
+oid sha256:549edf3725e96eec68d26df4f6f75ef221b3457f097cf83a673ce055b0ff4363
 size 498858859

wandb/run-20210726_001233-17u6inbn/files/output.log

@@ -19742,6 +19742,1540 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 
 
 
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Step... (29000/50000 | Loss: 1.6177186965942383, Acc: 0.67269366979599):  60%|█████████████████▍           | 30000/50000 [12:00:13<8:31:46,  1.54s/it]
+Evaluating ...:   0%|                                                                                                         | 0/130 [00:00<?, ?it/s]
+Step... (29500 | Loss: 1.6591482162475586, Learning Rate: 0.00024848486646078527)
+
+
+
+
+
+
+
+
+
+
+
+
+[14:08:36] - INFO - __main__ - Saving checkpoint at 30000 steps█████████████████████████████████████████████████████| 130/130 [00:21<00:00,  4.59it/s]
+All Flax model weights were used when initializing RobertaForMaskedLM.
+Some weights of RobertaForMaskedLM were not initialized from the Flax model and are newly initialized: ['lm_head.decoder.weight', 'roberta.embeddings.position_ids', 'lm_head.decoder.bias']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Step... (30000/50000 | Loss: 1.6142958402633667, Acc: 0.6730945110321045):  62%|████████████████▋          | 31000/50000 [12:25:40<6:58:17,  1.32s/it]
+Evaluating ...:  14%|█████████████▎                                                                                  | 18/130 [00:01<00:07, 15.90it/s]
+Step... (30500 | Loss: 1.712971806526184, Learning Rate: 0.00023636363039258868)
+
+
+
+
+
+
+
+
+
+
+
+
+[14:34:03] - INFO - __main__ - Saving checkpoint at 31000 steps█████████████████████████████████████████████████████| 130/130 [00:21<00:00,  4.60it/s]
+All Flax model weights were used when initializing RobertaForMaskedLM.
+Some weights of RobertaForMaskedLM were not initialized from the Flax model and are newly initialized: ['lm_head.decoder.weight', 'roberta.embeddings.position_ids', 'lm_head.decoder.bias']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 
 
 

wandb/run-20210726_001233-17u6inbn/files/wandb-summary.json

@@ -1 +1 @@
-{"global_step": 29000, "_timestamp": 1627306978.644497, "train_time": 1608587.125, "train_learning_rate": 0.00025454547721892595, "_step": 57826, "train_loss": 1.61568021774292, "eval_accuracy": 0.671392560005188, "eval_loss": 1.627186894416809}
+{"global_step": 31000, "_timestamp": 1627310015.206409, "train_time": 1810641.125, "train_learning_rate": 0.00023030306329019368, "_step": 61814, "train_loss": 1.6786357164382935, "eval_accuracy": 0.6730945110321045, "eval_loss": 1.6142958402633667}

wandb/run-20210726_001233-17u6inbn/logs/debug-internal.log

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94c5b08086a46b44790fad9ed823f1a906f51889fca276b7086bf41d20a3a8ce
-size 22872190
+oid sha256:9f796f543dac0ebb90fd654d77cc33441df5f7b3517d66f26e0456f3e2f83d06
+size 24483658

wandb/run-20210726_001233-17u6inbn/run-17u6inbn.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f83135fb6bd2b5e62d5771f3ca67b4afa426518c31fb39f682e6d326f6393e00
-size 11452146
+oid sha256:4e7542027cf0f1a8fe825b6101a9e222367928ba7623d6b21687570cfcac54f7
+size 12299882